Some checks failed
go: build dev binaries / cleanup (push) Successful in 4s
Codespell / Check for spelling errors (push) Failing after 3s
docker: build dev containers / build-rust-binaries (amd64, x86_64-unknown-linux-musl) (push) Failing after 3s
docker: build dev containers / build-dev-containers (push) Has been skipped
docker: build dev containers / build-rust-binaries (arm64, true, aarch64-unknown-linux-musl) (push) Failing after 3s
End to End / FUSE Mount (push) Failing after 2s
EC Integration Tests / EC Integration Tests (push) Failing after 30s
FUSE DLM Integration Tests / FUSE DLM Integration Tests (push) Failing after 3s
FUSE Volume Server Failover Tests / FUSE Volume Server Failover (push) Failing after 3s
FUSE Integration Tests / FUSE Integration Testing (push) Failing after 2s
FUSE P2P Peer Chunk Sharing Integration Tests / FUSE P2P Peer Chunk Sharing (push) Failing after 3s
go: build binary / Go Vet (push) Failing after 2s
go: build binary / Go Vet 32-bit (push) Failing after 3s
go: build binary / Build (push) Failing after 4s
go: build binary / Build cross-platform (freebsd/amd64) (push) Failing after 3s
go: build binary / Build cross-platform (windows/amd64) (push) Failing after 3s
go: build binary / Build cross-platform (darwin/arm64) (push) Failing after 3s
go: build binary / Build cross-platform (windows/arm64) (push) Failing after 3s
go: build binary / Test (push) Failing after 2s
go: build binary / Test 32-bit (push) Failing after 3s
helm: lint and test charts / lint-test (push) Failing after 3s
Java Client Integration Tests / Java Integration Tests (11) (push) Failing after 3s
Java Client Integration Tests / Java Integration Tests (17) (push) Failing after 3s
go: build dev binaries / build_dev_linux_windows (amd64, linux) (push) Failing after 2s
go: build dev binaries / build_dev_linux_windows (amd64, windows) (push) Failing after 3s
go: build dev binaries / build_dev_darwin (amd64, darwin) (push) Has been skipped
go: build dev binaries / build_dev_darwin (arm64, darwin) (push) Has been skipped
Java Client Unit Tests / Java Unit Tests (11) (push) Failing after 3s
Java Client Unit Tests / Java Unit Tests (17) (push) Failing after 2s
Java Client Unit Tests / Java Unit Tests (21) (push) Failing after 3s
Java Client Unit Tests / Java Unit Tests (8) (push) Failing after 3s
Kafka Quick Test (Load Test with Schema Registry) / Kafka Client Load Test (Quick) (push) Failing after 3s
Kafka Gateway Tests / Kafka Unit Tests (unit-tests-1) (push) Failing after 11s
Kafka Gateway Tests / Kafka Integration Tests (Critical) (integration-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka End-to-End Tests (with SMQ) (e2e-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka Consumer Group Tests (Highly Isolated) (consumer-group-1) (push) Failing after 2s
Kafka Gateway Tests / Kafka Client Compatibility (with SMQ) (client-compat-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka SMQ Integration Tests (Full Stack) (smq-integration-1) (push) Failing after 3s
Kafka Gateway Tests / Kafka Protocol Tests (Isolated) (protocol-1) (push) Failing after 3s
KMS Tests / KMS Provider Integration Tests (push) Failing after 2s
KMS Tests / S3 KMS End-to-End Tests (push) Failing after 3s
Master Cold Start Tests / Master Cold Start Tests (push) Failing after 4s
Metadata Subscribe Integration Tests / Metadata Subscribe Integration Tests (push) Failing after 3s
Multi-Master Tests / Multi-Master Failover Tests (push) Failing after 3s
Performance / CPU and Heap Profile (push) Failing after 2s
Performance / S3 Read/Write Benchmark (rust volume) (push) Failing after 3s
pjdfstest POSIX Compliance / pjdfstest (push) Failing after 2s
Plugin Worker Integration Tests / Plugin Worker: erasure_coding (push) Failing after 3s
Plugin Worker Integration Tests / Plugin Worker: vacuum (push) Failing after 3s
Rust Volume Server Tests / Rust Integration Tests (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 1) (push) Failing after 2s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 1) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 2) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 2) (push) Failing after 3s
Rust Volume Server Tests / Go Tests with Rust Volume (grpc - Shard 3) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Distributed Tests (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Performance Tests (push) Failing after 3s
Performance / Throughput Benchmark (go volume) (push) Failing after 3s
Performance / Throughput Benchmark (rust volume) (push) Failing after 2s
Performance / S3 Read/Write Benchmark (go volume) (push) Failing after 3s
Plugin Worker Integration Tests / Plugin Worker: volume_balance (push) Failing after 3s
PostgreSQL Gateway Tests / PostgreSQL Basic Tests (push) Failing after 3s
Rust Volume Server Tests / Rust Unit Tests (push) Failing after 2s
Rust Volume Server Tests / Go Tests with Rust Volume (http - Shard 3) (push) Failing after 3s
Rust Plugin Worker Tests / Rust Plugin Worker Build and Unit Tests (push) Failing after 3s
rust: build dev volume server binaries / cleanup (push) Successful in 3s
S3 ETag and ACL Tests / S3 ETag + ACL Integration Tests (push) Failing after 3s
S3 IAM Integration Tests / IAM Unit Tests (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (advanced) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (basic) (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Integration Tests (group) (push) Failing after 3s
S3 IAM Integration Tests / S3 IAM Integration Tests (policy-enforcement) (push) Failing after 2s
S3 IAM Integration Tests / S3 IAM Integration Tests (sts) (push) Failing after 4s
S3 Keycloak Integration Tests / S3 Keycloak Integration Tests (push) Failing after 3s
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.11) (push) Failing after 3s
S3 PyArrow Parquet Tests / Go Unit Tests (Implicit Directory) (push) Has been cancelled
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.12) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-darwin (darwin-amd64, x86_64-apple-darwin) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-darwin (darwin-arm64, aarch64-apple-darwin) (push) Has been cancelled
rust: build dev volume server binaries / build-rust-volume-dev-linux (linux-amd64, x86_64-unknown-linux-gnu) (push) Has been cancelled
S3 PyArrow Parquet Tests / PyArrow Parquet Tests (Python 3.9) (push) Has been cancelled
S3 Proxy Signature Tests / S3 Proxy Signature Verification Tests (push) Has been cancelled
S3 SDK V2 Route Disambiguation Tests / S3 SDK V2 Routing Tests (push) Has been cancelled
S3 SSE Tests / S3 SSE Integration Tests (quick) (push) Has been cancelled
S3 SSE Tests / S3 SSE Compatibility Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Metadata Persistence Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Copy Operations Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Multipart Upload Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Performance Test (push) Has been cancelled
S3 SSE Tests / S3 Volume Encryption Test (push) Has been cancelled
S3 SSE Tests / S3 SSE Integration Tests (comprehensive) (push) Has been cancelled
Spark Integration Tests / Spark Integration Tests (push) Failing after 2s
Telemetry Integration Tests / telemetry-integration-test (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 1) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 1) (push) Failing after 3s
Ceph S3 tests / Basic S3 tests (KV store) (push) Has been cancelled
Ceph S3 tests / S3 Versioning & Object Lock tests (push) Has been cancelled
S3 Policy Integration Tests / S3 Policy Unit Tests (push) Failing after 3s
Ceph S3 tests / S3 CORS tests (push) Has been cancelled
Ceph S3 tests / SeaweedFS Custom S3 Copy tests (push) Has been cancelled
Ceph S3 tests / Basic S3 tests (SQL store) (push) Has been cancelled
test s3 over https using aws-cli / awscli-tests (push) Has been cancelled
TLS Rotation Integration Tests / TLS Rotation Integration Tests (push) Has been cancelled
Vacuum Integration Tests / Vacuum Integration Tests (push) Has been cancelled
S3 Policy Integration Tests / S3 Policy Variables Integration Tests (push) Failing after 3s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (advanced-policy) (push) Failing after 3s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (basic-policy) (push) Failing after 2s
S3 Policy Integration Tests / S3 Policy Enforcement Integration Tests (contextual-policy) (push) Failing after 4s
S3 Policy Integration Tests / Trusted Proxy Detection Tests (push) Failing after 2s
S3 Policy Integration Tests / S3 Policy Shell Integration Tests (push) Failing after 3s
Samba on FUSE Integration / samba-integration (push) Failing after 2s
SFTP Integration Tests / SFTP Integration Testing (push) Failing after 3s
terraform: validate and test modules / fmt, validate, plan-level tests (push) Failing after 3s
terraform: validate and test modules / local cluster smoke test (real weed) (push) Failing after 2s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 3) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (grpc - Shard 2) (push) Failing after 3s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 2) (push) Failing after 2s
Volume Server Integration Tests / Volume Server Integration Tests (http - Shard 3) (push) Failing after 5s
mount: windows conformance / WinFsp conformance (push) Has been cancelled
mount: windows / Mount on Windows (push) Has been cancelled
273 lines
8.0 KiB
Go
273 lines
8.0 KiB
Go
package chunk_cache
|
|
|
|
import (
|
|
"encoding/binary"
|
|
"errors"
|
|
"sync"
|
|
|
|
"github.com/seaweedfs/seaweedfs/weed/glog"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/needle"
|
|
"github.com/seaweedfs/seaweedfs/weed/storage/types"
|
|
)
|
|
|
|
var ErrorOutOfBounds = errors.New("attempt to read out of bounds")
|
|
|
|
const cacheHeaderSize = 8 // 4 bytes volumeId + 4 bytes cookie
|
|
|
|
// parseCacheHeader extracts volume ID and cookie from the 8-byte cache header
|
|
func parseCacheHeader(header []byte) (needle.VolumeId, types.Cookie) {
|
|
volumeId := needle.VolumeId(binary.BigEndian.Uint32(header[0:4]))
|
|
cookie := types.BytesToCookie(header[4:8])
|
|
return volumeId, cookie
|
|
}
|
|
|
|
type ChunkCache interface {
|
|
ReadChunkAt(data []byte, fileId string, offset uint64) (n int, err error)
|
|
SetChunk(fileId string, data []byte)
|
|
IsInCache(fileId string, lockNeeded bool) (answer bool)
|
|
GetMaxFilePartSizeInCache() (answer uint64)
|
|
}
|
|
|
|
// a global cache for recently accessed file chunks
|
|
type TieredChunkCache struct {
|
|
memCache *ChunkCacheInMemory
|
|
diskCaches []*OnDiskCacheLayer
|
|
sync.RWMutex
|
|
onDiskCacheSizeLimit0 uint64
|
|
onDiskCacheSizeLimit1 uint64
|
|
onDiskCacheSizeLimit2 uint64
|
|
maxFilePartSizeInCache uint64
|
|
}
|
|
|
|
var _ ChunkCache = &TieredChunkCache{}
|
|
|
|
func NewTieredChunkCache(maxEntries int64, dir string, diskSizeInUnit int64, unitSize int64) *TieredChunkCache {
|
|
|
|
c := &TieredChunkCache{
|
|
memCache: NewChunkCacheInMemory(maxEntries),
|
|
}
|
|
c.diskCaches = make([]*OnDiskCacheLayer, 3)
|
|
c.onDiskCacheSizeLimit0 = uint64(unitSize)
|
|
c.onDiskCacheSizeLimit1 = 4 * c.onDiskCacheSizeLimit0
|
|
c.onDiskCacheSizeLimit2 = 2 * c.onDiskCacheSizeLimit1
|
|
c.diskCaches[0] = NewOnDiskCacheLayer(dir, "c0_2", diskSizeInUnit*unitSize/8, 2)
|
|
c.diskCaches[1] = NewOnDiskCacheLayer(dir, "c1_3", diskSizeInUnit*unitSize/4+diskSizeInUnit*unitSize/8, 3)
|
|
c.diskCaches[2] = NewOnDiskCacheLayer(dir, "c2_2", diskSizeInUnit*unitSize/2, 2)
|
|
c.maxFilePartSizeInCache = uint64(unitSize*diskSizeInUnit) / 4
|
|
|
|
return c
|
|
}
|
|
|
|
func (c *TieredChunkCache) GetMaxFilePartSizeInCache() (answer uint64) {
|
|
if c == nil {
|
|
return 0
|
|
}
|
|
return c.maxFilePartSizeInCache
|
|
}
|
|
|
|
func (c *TieredChunkCache) IsInCache(fileId string, lockNeeded bool) (answer bool) {
|
|
if c == nil {
|
|
return false
|
|
}
|
|
|
|
if lockNeeded {
|
|
c.RLock()
|
|
defer c.RUnlock()
|
|
}
|
|
|
|
item := c.memCache.cache.Get(fileId)
|
|
if item != nil {
|
|
glog.V(4).Infof("fileId %s is in memcache", fileId)
|
|
return true
|
|
}
|
|
|
|
fid, err := needle.ParseFileIdFromString(fileId)
|
|
if err != nil {
|
|
glog.V(4).Infof("failed to parse file id %s", fileId)
|
|
return false
|
|
}
|
|
|
|
// Check disk cache with volume ID and cookie validation
|
|
for i, diskCacheLayer := range c.diskCaches {
|
|
for k, v := range diskCacheLayer.diskCaches {
|
|
if nv, ok := v.nm.Get(fid.Key); ok {
|
|
// Read cache header to check volume ID and cookie
|
|
headerBytes := make([]byte, cacheHeaderSize)
|
|
if readN, readErr := v.DataBackend.ReadAt(headerBytes, nv.Offset.ToActualOffset()); readErr == nil && readN == cacheHeaderSize {
|
|
// Parse volume ID and cookie from header
|
|
storedVolumeId, storedCookie := parseCacheHeader(headerBytes)
|
|
|
|
if storedVolumeId == fid.VolumeId && storedCookie == fid.Cookie {
|
|
glog.V(4).Infof("fileId %s is in diskCaches[%d].volume[%d]", fileId, i, k)
|
|
return true
|
|
}
|
|
glog.V(4).Infof("fileId %s header mismatch in diskCaches[%d].volume[%d]: stored volume %d cookie %x, expected volume %d cookie %x",
|
|
fileId, i, k, storedVolumeId, storedCookie, fid.VolumeId, fid.Cookie)
|
|
}
|
|
}
|
|
}
|
|
}
|
|
return false
|
|
}
|
|
|
|
func (c *TieredChunkCache) ReadChunkAt(data []byte, fileId string, offset uint64) (n int, err error) {
|
|
if c == nil {
|
|
return 0, nil
|
|
}
|
|
|
|
c.RLock()
|
|
defer c.RUnlock()
|
|
|
|
minSize := offset + uint64(len(data))
|
|
if minSize <= c.onDiskCacheSizeLimit0 {
|
|
n, err = c.memCache.readChunkAt(data, fileId, offset)
|
|
if err != nil {
|
|
glog.Errorf("failed to read from memcache: %s", err)
|
|
}
|
|
if n == int(len(data)) {
|
|
return n, nil
|
|
}
|
|
}
|
|
|
|
fid, err := needle.ParseFileIdFromString(fileId)
|
|
if err != nil {
|
|
glog.Errorf("failed to parse file id %s", fileId)
|
|
return 0, nil
|
|
}
|
|
|
|
// Try disk caches with volume ID and cookie validation
|
|
if minSize <= c.onDiskCacheSizeLimit0 {
|
|
n, err = c.readChunkAtWithHeaderValidation(data, fid, offset, 0)
|
|
if n == int(len(data)) {
|
|
return
|
|
}
|
|
}
|
|
if minSize <= c.onDiskCacheSizeLimit1 {
|
|
n, err = c.readChunkAtWithHeaderValidation(data, fid, offset, 1)
|
|
if n == int(len(data)) {
|
|
return
|
|
}
|
|
}
|
|
{
|
|
n, err = c.readChunkAtWithHeaderValidation(data, fid, offset, 2)
|
|
if n == int(len(data)) {
|
|
return
|
|
}
|
|
}
|
|
|
|
return 0, nil
|
|
|
|
}
|
|
|
|
func (c *TieredChunkCache) SetChunk(fileId string, data []byte) {
|
|
if c == nil {
|
|
return
|
|
}
|
|
c.Lock()
|
|
defer c.Unlock()
|
|
|
|
glog.V(4).Infof("SetChunk %s size %d\n", fileId, len(data))
|
|
if c.IsInCache(fileId, false) {
|
|
glog.V(4).Infof("fileId %s is already in cache", fileId)
|
|
return
|
|
}
|
|
|
|
c.doSetChunk(fileId, data)
|
|
}
|
|
|
|
func (c *TieredChunkCache) doSetChunk(fileId string, data []byte) {
|
|
// Disk cache format: [4-byte volumeId][4-byte cookie][chunk data]
|
|
// Memory cache format: full fileId as key -> raw data (unchanged)
|
|
|
|
// Memory cache unchanged - uses full fileId
|
|
if len(data) <= int(c.onDiskCacheSizeLimit0) {
|
|
c.memCache.SetChunk(fileId, data)
|
|
}
|
|
|
|
fid, err := needle.ParseFileIdFromString(fileId)
|
|
if err != nil {
|
|
glog.Errorf("failed to parse file id %s", fileId)
|
|
return
|
|
}
|
|
|
|
// Prepend volume ID and cookie to data for disk cache
|
|
// Format: [4-byte volumeId][4-byte cookie][chunk data]
|
|
headerBytes := make([]byte, cacheHeaderSize)
|
|
// Store volume ID in first 4 bytes using big-endian
|
|
binary.BigEndian.PutUint32(headerBytes[0:4], uint32(fid.VolumeId))
|
|
// Store cookie in next 4 bytes
|
|
types.CookieToBytes(headerBytes[4:8], fid.Cookie)
|
|
dataWithHeader := append(headerBytes, data...)
|
|
|
|
// Store with volume ID and cookie header in disk cache
|
|
if len(data) <= int(c.onDiskCacheSizeLimit0) {
|
|
c.diskCaches[0].setChunk(fid.Key, dataWithHeader)
|
|
} else if len(data) <= int(c.onDiskCacheSizeLimit1) {
|
|
c.diskCaches[1].setChunk(fid.Key, dataWithHeader)
|
|
} else {
|
|
c.diskCaches[2].setChunk(fid.Key, dataWithHeader)
|
|
}
|
|
|
|
}
|
|
|
|
func (c *TieredChunkCache) Shutdown() {
|
|
if c == nil {
|
|
return
|
|
}
|
|
c.Lock()
|
|
defer c.Unlock()
|
|
for _, diskCache := range c.diskCaches {
|
|
diskCache.shutdown()
|
|
}
|
|
}
|
|
|
|
// readChunkAtWithHeaderValidation reads from disk cache with volume ID and cookie validation
|
|
func (c *TieredChunkCache) readChunkAtWithHeaderValidation(data []byte, fid *needle.FileId, offset uint64, cacheLevel int) (n int, err error) {
|
|
// Step 1: Read and validate header (volume ID + cookie)
|
|
headerBuffer := make([]byte, cacheHeaderSize)
|
|
headerRead, err := c.diskCaches[cacheLevel].readChunkAt(headerBuffer, fid.Key, 0)
|
|
|
|
if err != nil {
|
|
glog.V(4).Infof("failed to read header for %s from cache level %d: %v",
|
|
fid.String(), cacheLevel, err)
|
|
return 0, err
|
|
}
|
|
|
|
if headerRead < cacheHeaderSize {
|
|
glog.V(4).Infof("insufficient data for header validation for %s from cache level %d: read %d bytes",
|
|
fid.String(), cacheLevel, headerRead)
|
|
return 0, nil // Not enough data for header - likely old format, treat as cache miss
|
|
}
|
|
|
|
// Parse volume ID and cookie from header
|
|
storedVolumeId, storedCookie := parseCacheHeader(headerBuffer)
|
|
|
|
// Validate both volume ID and cookie
|
|
if storedVolumeId != fid.VolumeId || storedCookie != fid.Cookie {
|
|
glog.V(4).Infof("header mismatch for %s in cache level %d: stored volume %d cookie %x, expected volume %d cookie %x (possible old format)",
|
|
fid.String(), cacheLevel, storedVolumeId, storedCookie, fid.VolumeId, fid.Cookie)
|
|
return 0, nil // Treat as cache miss - could be old format or actual mismatch
|
|
}
|
|
|
|
// Step 2: Read actual data from the offset position (after header)
|
|
// The disk cache has format: [4-byte volumeId][4-byte cookie][actual chunk data]
|
|
// We want to read from position: cacheHeaderSize + offset
|
|
dataOffset := cacheHeaderSize + offset
|
|
n, err = c.diskCaches[cacheLevel].readChunkAt(data, fid.Key, dataOffset)
|
|
|
|
if err != nil {
|
|
glog.V(4).Infof("failed to read data at offset %d for %s from cache level %d: %v",
|
|
offset, fid.String(), cacheLevel, err)
|
|
return 0, err
|
|
}
|
|
|
|
return n, nil
|
|
}
|
|
|
|
func min(x, y int) int {
|
|
if x < y {
|
|
return x
|
|
}
|
|
return y
|
|
}
|